Nested Algorithms for Optimal Reservoir Operation and Their Embedding in a Decision Support Platform

Reservoir management is a highly complex problem, which includes the uncertainty in the inflows as well as in the objectives. Stochastic dynamic programming (SDP) has been widely used to develop the optimal operating policies of multipurpose reservoirs. In the recent years, fuzzy optimization has been used to incorporate the uncertainty caused due to the imprecise nature of objectives. In the present study, a comparison is made between a conventional SDP model and fuzzy dynamic programming models for optimal operation of a multipurpose reservoir. The two models are developed for Hirakud Reservoir on River Mahanadi in the State of Orissa in India. The performance of the reservoir is evaluated under the operating policies derived from these models through simulation. The results indicate that the fuzzy dynamic programming model performs better in achieving the flood control objective and thus in the overall performan1ce of reservoir.

Reasonable optimal operation policy for complex multiple reservoir systems is very important for the safe and efficient utilization of water resources. The operation policy of multiple hydropower reservoirs should be optimized to maximize total hydropower generation, while ensuring flood control safety by effective and efficient storage and release policy of multiple reservoirs. To achieve this goal, a new meta-heuristic algorithm, salp swarm algorithm (SSA), is used to optimize the joint operation of multiple hydropower reservoirs for the first time. SSA is a competitive bio-inspired optimizer, which has received substantial attention from researchers in a wide variety of applications in finance, engineering, and science because of its little controlling parameters and adaptive exploratory behavior. However, it still faces few drawbacks such as lack of exploitation and local optima stagnation, leading to a slow convergence rate. In order to tackle these problems, multiple strategies combining sine cosine operator, opposition-based learning mechanism, and elitism strategy are applied to the original SSA. The sine cosine operator is applied to balance the exploration and exploitation over the course of iteration; the opposition-based learning mechanism is used to enhance the diversity of the swarm; and the elitism strategy is adopted to find global optima. Then, the improved SSA (ISSA) is compared with six well-known meta-heuristic algorithms on 23 classical benchmark functions. The results obtained demonstrate that ISSA outperforms most of the well-known algorithms. Then, ISSA is applied to optimal operation of multiple hydropower reservoirs in the real world. A multiple reservoir system, namely Xiluodu Reservoir and Xiangjiaba Rservoir, in the upper Yangtze River of China are selected as a case study. The results obtained show that the ISSA is able to solve a real-world optimization problem with complex constraints. In addition, for the typical flood with a 100 return period in 1954, the maximum hydropower generation of multiple hydropower reservoirs is about 6671 GWh in the case of completing the flood control task, increasing by 1.18% and 1.77% than SSA and Particle Swarm Optimization (PSO), respectively. Thus, ISSA can be used as an alternative effective and efficient tool for the complex optimization of multiple hydropower reservoirs. The water resources in the river basin can be further utilized by the proposed method to cope with the increasingly serious climate change.

A comprehensive Genetic Algorithm (GA) model has been developed and applied to derive optimal operational strategies of a multi-purpose reservoir, namely Perunchani Reservoir, in Kodaiyar Basin in Tamil Nadu, India. Most of the water resources problem involves uncertainty, in order to see that the GA model takes care of uncertainty in the input variable, the result of the GA model is compared with the performance of a detailed Stochastic Dynamic Programming (SDP) model. The SDP models are well established and proved that it takes care of uncertainty in-terms of either implicit or explicit approach. In the present study, the objective function of the models is set to minimize the annual sum of squared deviation from desired target release and desired storage volume. In the SDP model the optimal policies are derived by varying the state variables from 3 to 9 representative class intervals, and then the cases are evaluated for their performance using a simulation model for longer length of inflow data, generated using a Thomas–Fiering model. From the performance of the SDP model policies, it is found that the system encountered irrigation deficit, whereas GA model satisfied the demand to a greater extent. The sensitivity analysis of the GA model in selecting optimal population, optimal crossover probability and the optimal number of generations showed the values of 150, 0.76 and 175 respectively. On comparing the performance of SDP model policy with GA model, it is found that GA model has resulted in a lesser irrigation deficit. Thus based on the present case study, it may be concluded that the GA model performs better than the SDP model.

A Computer Simulation Tool for Single-purpose Reservoir Operators

The simulation elevation-surface area-storage interrelationship of a reservoir is a crucial task in developing ideal water release policies for reservoir and dam operations. In this study, an inclusive (stochastic dynamic programming-artificial neural network (SDP-ANN)) model was established and applied to obtain an ideal reservoir operation strategy for Sg. Langat reservoir in Malaysia. The problems associated with the management of water resources mostly relate to uncertainty and the stochastic nature of the reservoir inflow, and the SDP-ANN model is meant to consider uncertainty in the input parameters such as reservoir inflow and reservoir evaporation losses. The performance of the SDP-ANN model was compared to that of the stochastic dynamic programming-autoregression (AR) model. The primary aim of the model is to decrease the squared deviation from the desired water release, which we determined by comparing the SDP-AR and SDP-ANN model performances. The results indicate that the SDP-ANN model demonstrated greater resilience and reliability with a lower supply deficit. Consequently, the case study results confirm that the SDP-ANN model performs better than the SDP-AR model in obtaining the best parameters for the reservoir operation. Specifically, a comparison of the models shows that the proposed Model 2 increased the reliability and resilience of the system by 7.5% and 6.3%, respectively.

A proposed stochastic dynamic programming (SDP) method with uncertainties in stream flow and water demand is developed to calculate optimal reservoir operation rules. The SDP method extends the classic SDP method that considers only one uncertainty in its operation rules. Time series of reservoir inflow and agricultural water demand for the Aydoghmoush Reservoir in eastern Azarbayejan, Iran, were obtained from meteorological data, available climate parameters, hydrologic data, and crop water demand. The application of the developed SDP with two uncertainties was evaluated with operation rules corresponding to four different scenarios, and optimal reservoir releases were determined for a drought year. Reservoir operation results were evaluated with different performance indices. This study's results demonstrate the advantage of considering uncertainties in reservoir inflow and water demand with the SDP method. The developed SDP method has general applicability under a range of climatic conditions, and the calculated operation rules cover the expected ranges of streamflow and water demand during the operating years.

The natural flow regime can sustain the ecological integrity of riverine ecosystems. Different reservoir operation polices differ in their effects on the degree of alteration of natural flow regimes. Dynamic programming plays an important role in developing operation policies. When using dynamic programming models to develop operation policies, the discrete number of storage states (DNSS), which is a key factor affecting the reservoirs operation policies, is always been determined based on computational efficiency and economic benefits. Little consideration has been given to the ecological disturbance caused by different DNSS‐based operation policies. To analyze the impact of DNSS, we built a deterministic dynamic programming model to explore the relationship among DNSS, the flow regime alteration (ecological disturbance), and the cumulative annual power generation (economic benefits) by setting a range of DNSS scenarios. We used three reservoirs with different storage coefficients (ratios of usable storage to annual average runoff) as examples and used the range of variability approach to assess the ecological disturbance under these scenarios. We compared the results with those of a stochastic dynamic programming (SDP) model and a Bayesian SDP (BSDP) model. We found that when DNSS is low, increasing DNSS improves economic benefits but causes a more severe ecological disturbance; when DNSS is high, increasing DNSS improves the economic benefits only slightly, without exacerbating the ecological disturbance; for a given DNSS, the BSDP model provides higher economic benefits than the SDP model and a similar disturbance of the riverine ecosystem; and larger reservoirs more often cause more severe disturbance of riverine ecosystems because monthly mean flows and annual extreme flows change more drastically. Our results will help to protect the riverine ecosystems and improve economic benefits if reservoir operation managers consider DNSS using dynamic programming models.

This article presents an innovative streamflow process model for use in reservoir operational rule design in stochastic dual dynamic programming (SDDP). Model features, which can be applied...

Inaccurate water release has occurred from Gunungrowo Reservoir. In May–June, there is excess water release from Gunungrowo Reservoir while in the period from July to August there is a shortage of water release. Therefore the reservoir operation should be evaluated and updated in order to obtain optimal results and to adjust the changes. The purpose of this study was to evaluate the existing reservoir operation and to carry out an optimization to find the optimal reservoir operation. The objective is to conduct hydrological analysis, evaluate the reservoir operation, formulate a model of reservoir operation, optimize the reservoir operation, and analyse the results of reservoir operation optimization. Optimization of reservoir operation generates the water level of reservoirs and the release of water in each period as well as the objective function value under each scenario of reservoir operation. The existing reservoir operation is not optimal and has a reliability of only 24%. In the operation of the existing reservoir, emptying of the reservoir storage always happens and inaccuracies in the release of water have occurred. The optimal reservoir operation is scenario I, with a reliability of 75%, in which water is released in Planting Season II and Planting Season III.

Recently, the demand of Wireless Sensor Network (WSN) increased rapidly due to the vast applications in environmental monitoring, health care, Smart cities, Industrial automation, agriculture and Transports, etc. However, limited battery backup in sensor nodes affects the lifetime of the WSN. In this paper, a novel multi objective optimization problem is formulated to maximize the life time by considering the distance distribution of sensor nodes with their Cluster Heads (CHs) and distribution of CH’s life time. The recent multi objective algorithms like Decomposition based Multi Objective Evolutionary (MOEAD), Multi Objective Grasshopper Algorithm (MOGOA), Multi Objective Particle Swarm Optimization (MOPSO), Multi Objective Grey Wolf optimization (MGWO) algorithm and Improved Multi Objective Differential Evolution (IMODE) algorithms are considered for the designing the multi-objective WSN and their performances are compared based on the scalability, lifetime, energy distribution and cluster distribution of sensor nodes. The simulation results demonstrated that MOEAD based WSN achieves 24.2% more life time than second best algorithms. Further, it achieves 97% (in average) accuracy in cluster quality. Moreover, MOEAD outperformed than other algorithms in Pareto optimal solution in terms of convergence, diversity and solution quality.

Synergistic gains from the multi-objective optimal operation of cascade reservoirs in the Upper Yellow River basin

Advanced control of large-scale wind turbines: Structural load reduction and lifetime control

Reservoirs play an important role within the water resources management framework. Among the available techniques for reservoir optimal operation, the most well known one is stochastic dynamic programming (SDP). In recent years, artificial intelligence techniques such as genetic algorithms (GA) and artificial neural networks have arisen as an alternative to overcome some of the limitations of traditional methods. Some of these limitations are related to the difficulty in combining SDP with other simulation and prediction models, the curse of dimensionality due to the increase in the number of decision and state variables, and the error resulting from the rough discretization of these variables. Here, we introduce a new approach for system optimization and operation, named stochastic fuzzy neural network (SFNN), which can be defined as a neuro-fuzzy system that is stochastically trained (optimized) by a GA model to represent the system operational strategy. Moreover, to deal with imprecision originated by the discretization of inflow intervals (events) in calculating the transition probabilities, we applied the method based on the conditional probability of a fuzzy event. To investigate the applicability and efficiency of the proposed method, the Barra Bonita Reservoir, Brazil, is stochastically optimized and operated. The results found by the SFNN method were compared to the results of other available dynamic programming models, showing success in developing and applying the proposed method to optimal reservoir operation.

Multi-objective reservoir operation during flood season considering spillway optimization

<p>The increasing stress on water resource systems has prompted researchers to look for ways to improve the performance of reservoir operations. Changes in demand, various hydrological inputs, and new environmental stresses are among issues that water managers face. These concerns have sparked interest in applying different techniques to determine reservoir operation policy to improve reservoir system performance. As the resolution of analysis rises, it becomes more difficult to effectively represent a real-world system using currently available approaches for determining the best reservoir operation policy. One of the challenges is the "curse of dimensionality," which occurs when the discretization of the state and action spaces becomes finer or when more state or action variables are taken into account. Because of the dimensionality curse, the number of state-action variables is limited, rendering dynamic programming (DP) and stochastic DP (SDP) ineffective in handling complex reservoir optimization issues. Reinforcement learning (RL) is one way to overcome the aforementioned curses of stochastic optimization of water resources systems. RL is a well-known and influential technique in machine learning research that can solve a wide range of optimization and simulation challenges. In this study, a novel continuous-action deep RL algorithm called Deep Deterministic Policy Gradients (DDPG) is applied to solve the DP problem for the Folsom Reservoir system located in California, US. Without requiring any model simplifications or surrendering any of the critical characteristics of DP, the employed continuous action-space RL method effectively overcomes dimensionality concerns. The system model employs an iterative learning method that takes into account delayed rewards without requiring an explicit probabilistic model of hydrologic processes, and it can learn the best actions that maximize total expected reward by interacting with a simulated environment. This research is funded by the US Geological Survey.</p>